Deep linguistic learning for email responses

This has been showing up in the usual places (even on my Facebook feed, today) and is good for some toothgrinding as I fervently wish I had more time to work like this.

Deep neural network classifies selfies

This is just a cool, well-written article.

Machine learning courses again

I may live to regret this (like I did in 2012), but I'm taking another stab at the MOOG machine learning courses. Well, the Stanford one at Coursera, anyway, but maybe I'll take another run at the Caltech one as well, after I'm done.

Some links, to keep them in a convenient place. Some are useful for actually doing the classes, some for understanding the math, and some ideas for what to do after the course, in no particular order.

• Main Coursera page for the course
• A decent presentation of the math behind least squares
• Partial derivative in gradient descent
• Coursera Wiki
• Deep Learning Tutorial at Stanford [hnn]
• Caltech's Learning from data course

So. Machine learning.

Update 2016-01-09: Unsurprisingly, I didn't have time for the Coursera run. Did break my word count record for 2015, though.

Naive Bayes and text classification

An introduction.

Simulated annealing in R

With a Web interface, no less!

Machine learning technique flowchart

Another flowchart for choosing between machine learning techniques.

Man, posting has been thin on the ground lately - our summer in the States was fantastic, though.

Deep learning 101

The latest!

This one weird kernel trick

Oneweirdkerneltrick. Very meta.

Machine learning to find memory leaks

This is pretty cool.

Numenta.org

Some kind of open-source machine learning project.

Course in Machine Learning

Another one.

One-class support vector machines

An introduction.

Machine learning for link spam

Double-whammy for tickling my fancy: a blow-by-blow account of applying machine learning to detection of link spam.

scikit-learn ML in Python

Python really is winning in the scientific programming arena.  The ML module of choice is scikit-learn.

Machine learning post roundup

Ugh, I've been falling behind in blogging out the links lately.  Here are a few things I've run across having to do with machine learning, NLP, and neural networks lately (all the stuff people don't call AI any more):

• Ersatz is an upcoming platform for neural network training in the cloud.  Neat!
• Topology optimization for physical structures with genetic programming, with a fun animation
• A CMU class in ML
• Sentiment analysis in Python
• A field guide to genetic programming, nice name
  
  And finally, an interesting post about the background:
• Prognistication about the future of the ML industry

Neural networks

I need to spend more time with personal development.

Data sources

Another cool post about finding neat data sets.

Learning algorithms in Haskell

Hmm, this makes sense for Haskell, I think - really, anything mathematical makes sense for Haskell.  Note to self: really.  Learn you some Haskell.

Also: this.  I think the time has come.

Common machine learning mistakes

Common mistakes applying machine learning to financial modeling - but they're common mistakes made in applying machine learning to anything.  Worth reading.

Data science in HFT

Oooh, financial AI, always an interesting topic!  And a great article, too.